setup-matt-pocock-skills
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local CLI tools including
git,gh(GitHub CLI), andglab(GitLab CLI) to inspect repository status and provide instructions for managing issue trackers. These operations are scoped to the project's metadata and issue management. - [SAFE]: The skill implements a robust human-in-the-loop safety mechanism by requiring a "Confirm and edit" step (Step 3). The agent must present all proposed changes and configuration drafts to the user for review and manual editing before any files are written to the disk.
- [SAFE]: The skill processes repository state and documentation which are potential surfaces for indirect prompt injection.
- Ingestion points: Reads repository metadata via
git remote, project configuration files (package.json,pnpm-workspace.yaml), and existing documentation (CLAUDE.md,CONTEXT.md). - Boundary markers: A mandatory user confirmation phase is present before any write operations.
- Capability inventory: File system writes (creating documentation in
docs/agents/), file modifications (updatingCLAUDE.mdorAGENTS.md), and shell command execution (git,gh,glab). - Sanitization: Relies on the user as a manual validation gate for all generated output.
Audit Metadata